How to run AudioGen Medium locally

Meta · Text → audio · 1.5B params · CC-BY-NC-4.0 (non-commercial)

A text-to-audio model specialized in realistic environmental sound effects like barking, sirens and footsteps from text descriptions.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 8.0 GB of VRAM (~8GB fp16; 16kHz environmental audio), via AudioCraft.
Rent a GPU — from $0.26/hr. Fits RTX 3090 24GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
Download the weights — free. Open weights at facebook/audiogen-medium.

Note: generative-media models are billed per image / per second / per minute on hosted services — not per token. Running locally or on your own rented GPU is usually far cheaper and keeps your data on your machine.

Key facts

Does	Text → audio
VRAM to run	~8.0 GB (~8GB fp16; 16kHz environmental audio)
Download	~6 GB
Parameters	1.5B
License	CC-BY-NC-4.0 (non-commercial)
Run with	AudioCraft

Get AudioGen Medium on Hugging Face →

More voice & audio models

Whisper large-v3 — Speech → text, ~10 GB VRAM
Whisper large-v3-turbo — Speech → text, ~6.0 GB VRAM
Kokoro-82M — Text → speech, ~1.0 GB VRAM
XTTS-v2 — Voice cloning, ~6.0 GB VRAM
MusicGen Large — Text → music, ~16 GB VRAM
Chatterbox — Text → speech, ~8.0 GB VRAM

Browse: all media models · chat / LLM models